VL-RewardBench

Dataset Card for VLRewardBench Project Page: https://vl-rewardbench.github.io Dataset Summary VLRewardBench is a comprehensive benchmark designed to evaluate vision-language generative reward models (VL-GenRMs) across visual perception, hallucination detection, and reasoning tasks. The benchmark contains 1,250 high-qua

Papers using VL-RewardBench (4)

DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification2026R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning2025BaseReward: A Strong Baseline for Multimodal Reward Model2025Self-Improving VLM Judges Without Human Annotations2025